{"id":"W2113944588","doi":"10.1093/bioinformatics/btn433","title":"Accurate sequence-based prediction of catalytic residues","year":2008,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Machine Learning in Bioinformatics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":85,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Nankai University","keywords":"Support vector machine; Curse of dimensionality; Sequence (biology); Computer science; Classifier (UML); Protein structure prediction; Feature selection; Artificial intelligence; Biological system; Data mining; Pattern recognition (psychology); Protein structure; Chemistry; Biology; Biochemistry","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001965857,0.0001582458,0.0001639965,0.00008781871,0.0001061629,0.00001199356,0.0002401312,0.0001505152,0.0000142338],"category_scores_gemma":[0.0002597765,0.0001421885,0.00008579824,0.0001447371,0.0001881718,0.00001779626,0.00007282638,0.0001084505,0.00003681927],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001864774,"about_ca_system_score_gemma":0.0002096762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001326527,"about_ca_topic_score_gemma":0.000004286005,"domain_scores_codex":[0.9988642,0.000023092,0.0005599108,0.00009711723,0.0002453457,0.0002103603],"domain_scores_gemma":[0.9989862,0.00002001109,0.0003193919,0.0004607067,0.000140494,0.00007320621],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001577343,0.001232331,0.3538381,0.006312343,0.001176217,0.00005293434,0.01507288,0.1254538,0.2429012,0.002539364,0.2164298,0.03341367],"study_design_scores_gemma":[0.003024219,0.001848285,0.03851151,0.0002011507,0.00009503387,0.0003010558,0.0005523268,0.5443331,0.3453241,0.00005258086,0.06484751,0.0009090563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9414378,0.000130545,0.03953401,0.0001187483,0.000280164,0.0004288964,0.0002838111,0.00009670048,0.01768932],"genre_scores_gemma":[0.9678375,0.0001038654,0.03064948,0.0002277495,0.00008060606,0.000008977158,0.0007035214,0.0000170239,0.0003713224],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4188793,"threshold_uncertainty_score":0.579828,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02821141345171289,"score_gpt":0.2624030186154391,"score_spread":0.2341916051637262,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}